Class SpatialTransform<T>

Namespace

AiDotNet.Augmentation.Video

Assembly

AiDotNet.dll

Applies spatial transformations (flips, rotations) consistently to all frames.

public class SpatialTransform<T> : SpatialVideoAugmenterBase<T>, IAugmentation<T, ImageTensor<T>[]>

Type Parameters

T

The numeric type for calculations.

Inheritance

object

AugmentationBase<T, ImageTensor<T>[]>

VideoAugmenterBase<T>

SpatialVideoAugmenterBase<T>

SpatialTransform<T>

Implements

IAugmentation<T, ImageTensor<T>[]>

Inherited Members

SpatialVideoAugmenterBase<T>.ConsistentAcrossFrames

VideoAugmenterBase<T>.FrameRate

VideoAugmenterBase<T>.GetDuration(ImageTensor<T>[])

VideoAugmenterBase<T>.GetFrameCount(ImageTensor<T>[])

VideoAugmenterBase<T>.ValidateFrameDimensions(ImageTensor<T>[])

AugmentationBase<T, ImageTensor<T>[]>.NumOps

AugmentationBase<T, ImageTensor<T>[]>.OnAugmentationApplied

AugmentationBase<T, ImageTensor<T>[]>.Name

AugmentationBase<T, ImageTensor<T>[]>.Probability

AugmentationBase<T, ImageTensor<T>[]>.IsTrainingOnly

AugmentationBase<T, ImageTensor<T>[]>.IsEnabled

AugmentationBase<T, ImageTensor<T>[]>.Apply(ImageTensor<T>[], AugmentationContext<T>)

AugmentationBase<T, ImageTensor<T>[]>.ApplyAugmentation(ImageTensor<T>[], AugmentationContext<T>)

AugmentationBase<T, ImageTensor<T>[]>.GetParameters()

AugmentationBase<T, ImageTensor<T>[]>.RaiseAugmentationApplied(AugmentationContext<T>, bool)

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.MemberwiseClone()

object.ReferenceEquals(object, object)

object.ToString()

Remarks

For Beginners: Spatial transform applies image augmentations like horizontal flip or rotation to all frames in the video consistently. This ensures the transformation is coherent across the entire video.

Available transforms:

• Horizontal flip (mirror left-right)
• Vertical flip (mirror top-bottom)
• 90° rotation (clockwise)
• 180° rotation
• 270° rotation (counter-clockwise)

Constructors

SpatialTransform(double, double, double, double)

Creates a new spatial transform augmentation.

public SpatialTransform(double horizontalFlipProbability = 0.5, double verticalFlipProbability = 0.5, double probability = 0.5, double frameRate = 30)

Parameters

horizontalFlipProbability double

Probability of horizontal flip (default: 0.5).

verticalFlipProbability double

Probability of vertical flip (default: 0.5).

probability double

Probability of applying any transform (default: 0.5).

frameRate double

Frame rate of the video (default: 30).

Properties

EnableHorizontalFlip

Gets or sets whether to enable horizontal flip.

public bool EnableHorizontalFlip { get; set; }

Property Value

bool

EnableRotation90

Gets or sets whether to enable 90° rotations.

public bool EnableRotation90 { get; set; }

Property Value

bool

EnableVerticalFlip

Gets or sets whether to enable vertical flip.

public bool EnableVerticalFlip { get; set; }

Property Value

bool

HorizontalFlipProbability

Gets the probability of horizontal flip (when enabled).

public double HorizontalFlipProbability { get; }

Property Value

double

VerticalFlipProbability

Gets the probability of vertical flip (when enabled).

public double VerticalFlipProbability { get; }

Property Value

double

Methods

ApplyAugmentation(ImageTensor<T>[], AugmentationContext<T>)

Implement this method to perform the actual augmentation.

protected override ImageTensor<T>[] ApplyAugmentation(ImageTensor<T>[] data, AugmentationContext<T> context)

Parameters

data ImageTensor<T>[]

The input data.

context AugmentationContext<T>

The augmentation context.

Returns

ImageTensor<T>[]

The augmented data.

GetParameters()

Gets the parameters of this augmentation.

public override IDictionary<string, object> GetParameters()

Returns

IDictionary<string, object>

A dictionary of parameter names to values.